A Maximum Entropy-Based Bio-Molecular Event Extraction Model that Considers Event Generation
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we propose a maximum entropy-based model, which can mathematically explain the biomolecular event extraction problem. The proposed model generates an event table, which can represent the relationship between an event trigger and its arguments. The complex sentences with distinctive event structures can be also represented by the event table. Previous approaches intuitively designed a pipeline system, which sequentially performs trigger detection and arguments recognition, and thus, did not clearly explain the relationship between identified triggers and arguments. On the other hand, the proposed model generates an event table that can represent triggers, their arguments, and their relationships. The desired events can be easily extracted from the event table. Experimental results show that the proposed model can cover 91.36% of events in the training dataset and that it can achieve a 50.44% recall in the test dataset by using the event table.
Abstract
In this paper, we propose a maximum entropy-based model, which can mathematically explain the biomolecular event extraction problem. The proposed model generates an event table, which can represent the relationship between an event trigger and its arguments. The complex sentences with distinctive event structures can be also represented by the event table. Previous approaches intuitively designed a pipeline system, which sequentially performs trigger detection and arguments recognition, and thus, did not clearly explain the relationship between identified triggers and arguments. On the other hand, the proposed model generates an event table that can represent triggers, their arguments, and their relationships. The desired events can be easily extracted from the event table. Experimental results show that the proposed model can cover 91.36% of events in the training dataset and that it can achieve a 50.44% recall in the test dataset by using the event table.
참고문헌 (25)
- C. Blaschke, ""Automatic extraction of biological information from scientific text: protein-protein interactions", Proceedings of International Conference on Intelligent Systems for Molecular Biology, pp.60~67 (1999)
- R. Bunescu, "Integrating co-occurrence statistics with information extraction for robust retrieval of protein interactions from medline", Proceedings of the Workshop on Linking Natural Language Processing and Biology, pp.49~56 (2006)
- H. W. Chun, "Extraction of gene-disease relations from medline using domain dictionaries and machine learning", Proceedings of the Pacific Symposium on Biocomputing, pp.4~15 (2006)
- F. Rinaldi, "Mining of relations between proteins over biomedical scientific literature using a deep-linguistic approach", Artificial Intelligence in Medicine, 39(2), pp.127~136 (2007)
- A. Airola, "All-Paths Graph Kernel for Protein-Protein Interaction Extraction with Evaluation of Cross-corpus Learning", BMC Bioinformatics, 9(Suppl. 11) (2008)
- 박경미, "Utilizing Various Natural Language Processing Techniques for Biomedical Interaction Extraction", JIPS(Journal of Information Processing Systems), 7(3), pp.459~472 (2011), 한국정보처리학회
- J. D. Kim, "Extracting bio-molecular events from literature-the Bionlp’09 Shared Task", Computational Intelligence, 27(4), pp.513~540 (2011)
- J. Björne, "Extracting contextualized complex biological events with rich graph-based feature sets", Computational Intelligence, 27(4), pp.541~557 (2011)
- E. Buyko, "Syntactic simplification and semantic enrichment-trimming dependency graphs for event extraction", Computational Intelligence, 27(4), pp.610~644 (2011)
- K. Hacioglu, "Semantic Role Labeling Using Dependency Trees", Proceedings of the International Conference on Computational Linguistics (2004)
- R. T. H. Tsai, "Biosmile: adapting semantic role labeling for biomedical verbs: an exponential model coupled with automatically generated template features", Proceedings of the HLT-NAACL BioNLP Workshop on Linking Natural Language and Biology, pp.57~64 (2006)
- K. Fundel, "RelEx-relation extraction using dependency parse trees", Bioinformatics, 23(3), pp.365~371 (2007)
- H. Kilicoglu, "Effective bio-event extraction using trigger words and syntactic dependencies", Computational Intelligence, 27(4), pp.583~609 (2011)
- J. Hakenberg, "Molecular event extraction from link grammar parse trees in the BioNLP’09 Shared Task", Computational Intelligence, 27(4), pp.665~680 (2011)
- A. Vlachos, "Biomedical event extraction without training data", Proceedings of the BioNLP 2009 Workshop Companion Volume for Shared Task, pp.37~40 (2009)
- R. Morante, "A memory-based learning approach to event extraction in biomedical texts", Proceedings of the BioNLP 2009Workshop Companion Volume for Shared Task, pp.59~67 (2009)
- H. G. Lee, "A multi-phase approach to biomedical event extraction", Proceedings of the BioNLP 2009Workshop Companion Volume for Shared Task, pp.107~110 (2009)
- S. Riedel, "Bio-molecular event extraction with Markov logic", Computational Intelligence, 27(4), pp.558~582 (2011)
- S. Van Landeghem, "High-precision bio-molecular event extraction from text using parallel binary classifiers", Computational Intelligence, 27(4), pp.645~664 (2011)
- K. Sagae, "A best-first probabilistic shift-reduce parser", Proceedings of the COLING, 2006, 691~698
- E. Charniak, "Edgebased best-first chart parsing", Proceedings of the Sixth Workshop on Very Large Corpora, pp.127~133 (1998)
- A. L. Berger, "A maximum entropy approach to natural language processing", Computational Linguistics, 22(1), pp.39~71 (1996)
- T. Lukasiewicz, "Credal networks under maximum entropy", Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, pp.363~370 (2000)
- L. Zhang, "Maximum Entropy Modeling Toolkit for Python and C++", pp.2004
- A. Ratnaparkhi, "Learning to parse natural language with maximum entropy models", Machine Learning, 34(1-3), pp.151~175 (1999)